© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113677
    Prev
    Next
    INDEX
    Explanations

    two or three

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /Index
    -0.10
    endir
    -0.10
    opt
    -0.10
    ailles
    -0.10
    kre
    -0.10
    (er
    -0.10
     resolving
    -0.10
     blown
    -0.10
     onboard
    -0.10
    -lasting
    -0.10
    POSITIVE LOGITS
    undred
    0.12
     sided
    0.11
    ided
    0.10
     dimensional
    0.10
    armed
    0.09
     Armed
    0.09
     hundred
    0.09
     armed
    0.09
    eler
    0.09
     syll
    0.09
    Activations Density 0.052%

    No Known Activations